Seeing the Forest from the Trees: A Holistic Approach to Near-Infrared Heterogeneous Face Recognition

2016 ◽  
Author(s):  
Christopher Reale ◽  
Nasser M. Nasrabadi ◽  
Heesung Kwon ◽  
Rama Chellappa
Keyword(s):  
Face Recognition ◽  
Near Infrared ◽  
Holistic Approach ◽  
Heterogeneous Face Recognition

scholarly journals Disentangled Variational Representation for Heterogeneous Face Recognition

2019 ◽  
Vol 33 ◽  
pp. 9005-9012 ◽  
Author(s):  
Xiang Wu ◽  
Huaibo Huang ◽  
Vishal M. Patel ◽  
Ran He ◽  
Zhenan Sun
Keyword(s):  
Face Recognition ◽  
Latent Variable ◽  
Near Infrared ◽  
Heterogeneous Data ◽  
Face Representation ◽  
Identity Information ◽  
Variational Representation ◽  
Heterogeneous Face Recognition ◽  
Latent Space ◽  
Variable Space

Visible (VIS) to near infrared (NIR) face matching is a challenging problem due to the significant domain discrepancy between the domains and a lack of sufficient data for training cross-modal matching algorithms. Existing approaches attempt to tackle this problem by either synthesizing visible faces from NIR faces, extracting domain-invariant features from these modalities, or projecting heterogeneous data onto a common latent space for cross-modal matching. In this paper, we take a different approach in which we make use of the Disentangled Variational Representation (DVR) for crossmodal matching. First, we model a face representation with an intrinsic identity information and its within-person variations. By exploring the disentangled latent variable space, a variational lower bound is employed to optimize the approximate posterior for NIR and VIS representations. Second, aiming at obtaining more compact and discriminative disentangled latent space, we impose a minimization of the identity information for the same subject and a relaxed correlation alignment constraint between the NIR and VIS modality variations. An alternative optimization scheme is proposed for the disentangled variational representation part and the heterogeneous face recognition network part. The mutual promotion between these two parts effectively reduces the NIR and VIS domain discrepancy and alleviates over-fitting. Extensive experiments on three challenging NIR-VIS heterogeneous face recognition databases demonstrate that the proposed method achieves significant improvements over the state-of-the-art methods.

scholarly journals SADG: Self-Aligned Dual NIR-VIS Generation for Heterogeneous Face Recognition

2021 ◽  
Vol 11 (3) ◽  
pp. 987
Author(s):  
Pengcheng Zhao ◽  
Fuping Zhang ◽  
Jianming Wei ◽  
Yingbo Zhou ◽  
Xiao Wei
Keyword(s):  
Face Recognition ◽  
Near Infrared ◽  
External Information ◽  
Significant Alignment ◽  
Heterogeneous Face Recognition ◽  
Image Translation ◽  
Challenging Tasks ◽  
The Mean ◽  
Ablation Study ◽  
Public Datasets

Heterogeneous face recognition (HFR) has aroused significant interest in recent years, with some challenging tasks such as misalignment problems and limited HFR data. Misalignment occurs among different modalities’ images mainly because of misaligned semantics. Although recent methods have attempted to settle the low-shot problem, they suffer from the misalignment problem between paired near infrared (NIR) and visible (VIS) images. Misalignment can bring performance degradation to most image-to-image translation networks. In this work, we propose a self-aligned dual generation (SADG) architecture for generating semantics-aligned pairwise NIR-VIS images with the same identity, but without the additional guidance of external information learning. Specifically, we propose a self-aligned generator to align the data distributions between two modalities. Then, we present a multiscale patch discriminator to get high quality images. Furthermore, we raise the mean landmark distance (MLD) to test the alignment performance between NIR and VIS images with the same identity. Extensive experiments and an ablation study of SADG on three public datasets show significant alignment performance and recognition results. Specifically, the Rank1 accuracy achieved was close to 99.9% for the CASIA NIR-VIS 2.0, Oulu-CASIA NIR-VIS and BUAA VIS-NIR datasets, respectively.

Mutual Component Analysis for Heterogeneous Face Recognition

2016 ◽  
Vol 7 (3) ◽  
pp. 1-23 ◽  
Author(s):  
Zhifeng Li ◽  
Dihong Gong ◽  
Qiang Li ◽  
Dacheng Tao ◽  
Xuelong Li
Keyword(s):  
Face Recognition ◽  
Component Analysis ◽  
Heterogeneous Face Recognition

Partial NIR-VIS Heterogeneous Face Recognition With Automatic Saliency Search

2021 ◽  
Vol 16 ◽  
pp. 5003-5017
Author(s):  
Mandi Luo ◽  
Xin Ma ◽  
Zhihang Li ◽  
Jie Cao ◽  
Ran He
Keyword(s):  
Face Recognition ◽  
Heterogeneous Face Recognition

scholarly journals Coupled Discriminant Analysis for Heterogeneous Face Recognition

2012 ◽  
Vol 7 (6) ◽  
pp. 1707-1716 ◽  
Author(s):  
Zhen Lei ◽  
Shengcai Liao ◽  
Anil K. Jain ◽  
Stan Z. Li
Keyword(s):  
Face Recognition ◽  
Discriminant Analysis ◽  
Heterogeneous Face Recognition

Face Recognition, Near-Infrared

2015 ◽  
pp. 500-503
Author(s):  
Stan Z. Li ◽  
Dong Yi
Keyword(s):  
Face Recognition ◽  
Near Infrared
Sign in / Sign up

Export Citation Format

Share Document